Temporal Convolutions

Convolutional time-domain audio separation network

Introduced by Luo et al. in Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation

Combines learned time-frequency representation with a masker architecture based on 1D dilated convolution.

Source: Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Speech Separation 3 37.50%
Speech Enhancement 2 25.00%
Speaker Recognition 1 12.50%
Music Source Separation 1 12.50%
Speaker Separation 1 12.50%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories